C5T3

require(pacman)

pacman:: p_load(pacman, dplyr, GGally, ggplot2, ggrepel, patchwork, gifski, ggforce, ggthemes, maps, sf, concaveman, remotes, readxl, ggthemes, ggvis, httr, plotly, rmarkdown, extrafont, shiny, isoband, stringr, rio, tidyr, labeling, caret, jquerylib, farver, corrgram, caTools, cowplot, randomForest, RMariaDB, lubridate, zoo, scales, ggfortify, forecast, doParallel,e1071,C50,kknn)

Importing and Feature Selection

First step is to import the data and select the features that only apply to each phone.

###Original Data

df_iphone <- import("iphone_smallmatrix_labeled_8d.csv")
df_samsung <- import("galaxy_smallmatrix_labeled_9d.csv")

Histogram for EDA

plot_ly(df_iphone, x= ~df_iphone$iphonesentiment, type='histogram')

plot_ly(df_samsung, x= ~df_samsung$galaxysentiment, type='histogram')

Where:
0: Sentiment Unclear
1: very negative
2: somewhat negative
3: neutral
4: somewhat positive
5: very positive

###Domain Expertise Feature Selection

df_iphoneDE <- select(df_iphone, c(ios, iphonecampos, iphonecamneg, iphonecamunc, iphonedispos, iphonedisneg, iphonedisunc, iphoneperpos,iphoneperneg,iphoneperunc,iosperpos,iosperneg,iosperunc,iphonesentiment))

df_samsungDE <- select(df_samsung, c(googleandroid, samsungcampos, samsungcamneg, samsungcamunc, samsungdispos, samsungdisneg, samsungdisunc, samsungperpos,samsungperneg,samsungperunc,googleperpos,googleperneg,googleperunc,galaxysentiment))

###Correlation Feature Selection

Corrmatrix = cor(df_iphone)
Corrmatrix2 = cor(df_samsung)

#findCorrelation(Corrmatrix, cutoff = .8, verbose = TRUE, names = TRUE)
#findCorrelation(Corrmatrix2, cutoff = .8, verbose = TRUE, names = TRUE)

df_iphoneCOR <- select(df_iphone, c(samsungdisneg, samsungperneg, samsungdispos, htcdisneg,googleperneg, googleperpos, samsungdisunc, samsungcamunc, htcperpos,nokiacamunc,  nokiadisneg, nokiadispos, nokiaperunc, nokiacampos, nokiadisunc,nokiaperneg,nokiacamneg,iphonedisneg, 
iphonedispos,sonydispos, iosperunc, iosperneg, ios, htcphone,iphonesentiment))

df_samsungCOR <- select(df_samsung,c(samsungdisneg,samsungperneg,samsungdispos,htcdisneg,googleperneg,googleperpos,samsungdisunc,samsungcamunc,htcperpos,nokiacamunc,nokiadisneg,nokiadispos,nokiaperunc,nokiacampos,nokiadisunc,nokiaperneg,nokiacamneg,iphonedisneg,iphonedispos,sonyperpos,iosperunc,iosperneg,sonydisneg,ios,htcphone,galaxysentiment))

###NZV Feature Selection

Near zero variance feature selection

nzv_iphone <- nearZeroVar(df_iphone, saveMetrics = FALSE)
nzv_samsung <- nearZeroVar(df_samsung, saveMetrics = FALSE)

df_iphoneNZV <- df_iphone[,-nzv_iphone]
df_samsungNZV <- df_samsung[,-nzv_samsung]

#str(df_iphoneNZV)
#str(df_samsungNZV)

RFE Feature Selection

Let’s sample the data before using RFE

set.seed(123)
iphoneSample <- df_iphone[sample(1:nrow(df_iphone), 1000, replace=FALSE),]
samsungSample <- df_samsung[sample(1:nrow(df_samsung), 1000, replace=FALSE),]

Set up rfeControl with randomforest, repeated cross validation and no updates

ctrl <- rfeControl(functions = rfFuncs, method = "repeatedcv", repeats = 5, verbose = FALSE)

#cl <- makeCluster(7)
#registerDoParallel(cl)

# Use rfe and omit the response variable (attribute 59 iphonesentiment) 
rfeResults_iphone <- rfe(iphoneSample[,1:58], iphoneSample$iphonesentiment, sizes=(1:58), rfeControl=ctrl)
rfeResults_samsung <- rfe(samsungSample[,1:58], samsungSample$galaxysentiment, sizes=(1:58), rfeControl=ctrl)

# Get results
rfeResults_iphone

Recursive feature selection

Outer resampling method: Cross-Validated (10 fold, repeated 5 times) 

Resampling performance over subset size:

The top 5 variables (out of 20):
   iphone, googleandroid, iphonedispos, iphonedisneg, samsunggalaxy

rfeResults_samsung

Recursive feature selection

Outer resampling method: Cross-Validated (10 fold, repeated 5 times) 

Resampling performance over subset size:

The top 5 variables (out of 14):
   iphone, googleandroid, samsunggalaxy, iphonedispos, iphonecamunc

plot(rfeResults_iphone, type=c("g", "o"))

plot(rfeResults_samsung, type=c("g", "o"))

# create new data set with rfe recommended features
df_iphoneRFE <- df_iphone[,predictors(rfeResults_iphone)]
df_samsungRFE <- df_samsung[,predictors(rfeResults_samsung)]

# add the dependent variable to iphoneRFE
df_iphoneRFE$iphonesentiment <- df_iphone$iphonesentiment
df_samsungRFE$galaxysentiment <- df_samsung$galaxysentiment

All Data Sets

df_iphone Original Data
df_samsung

df_iphoneDE Domain Expertise
df_samsungDE

df_iphoneCOR Correlation
df_samsungCOR

df_iphoneNZV Near zero variance feature selection
df_samsungNZV

df_iphoneRFE Recursive Feature Elimination
df_samsungRFE

df_iphone$iphonesentiment <- factor(df_iphone$iphonesentiment)
df_samsung$galaxysentiment <- factor(df_samsung$galaxysentiment)

df_iphoneDE$iphonesentiment <- factor(df_iphoneDE$iphonesentiment)
df_samsungDE$galaxysentiment <- factor(df_samsungDE$galaxysentiment)

df_iphoneCOR$iphonesentiment <- factor(df_iphoneCOR$iphonesentiment)
df_samsungCOR$galaxysentiment <- factor(df_samsungCOR$galaxysentiment)

df_iphoneNZV$iphonesentiment <- factor(df_iphoneNZV$iphonesentiment)
df_samsungNZV$galaxysentiment <- factor(df_samsungNZV$galaxysentiment)

df_iphoneRFE$iphonesentiment <- factor(df_iphoneRFE$iphonesentiment)
df_samsungRFE$galaxysentiment <- factor(df_samsungRFE$galaxysentiment)

Model Development

Models with non-feature selected datasets and then feature selected data sets. C5.0, Random Forest, SVM, kknn

set.seed(123)

#iPhone

inTrain <- createDataPartition(df_iphone$iphonesentiment, p=.70, list = FALSE)
training_iphone <- df_iphone[ inTrain,]
testing_iphone  <- df_iphone[-inTrain,]

inTrain <- createDataPartition(df_iphoneDE$iphonesentiment, p=.70, list = FALSE)
training_iphoneDE <- df_iphoneDE[ inTrain,]
testing_iphoneDE  <- df_iphoneDE[-inTrain,]

inTrain <- createDataPartition(df_iphoneCOR$iphonesentiment, p=.70, list = FALSE)
training_iphoneCOR <- df_iphoneCOR[ inTrain,]
testing_iphoneCOR  <- df_iphoneCOR[-inTrain,]

inTrain <- createDataPartition(df_iphoneNZV$iphonesentiment, p=.70, list = FALSE)
training_iphoneNZV <- df_iphoneNZV[ inTrain,]
testing_iphoneNZV  <- df_iphoneNZV[-inTrain,]

inTrain <- createDataPartition(df_iphoneRFE$iphonesentiment, p=.70, list = FALSE)
training_iphoneRFE <- df_iphoneRFE[ inTrain,]
testing_iphoneRFE  <- df_iphoneRFE[-inTrain,]

#Samsung

inTrain <- createDataPartition(df_samsung$galaxysentiment, p=.70, list = FALSE)
training_samsung <- df_samsung[ inTrain,]
testing_samsung  <- df_samsung[-inTrain,]

inTrain <- createDataPartition(df_samsungDE$galaxysentiment, p=.70, list = FALSE)
training_samsungDE <- df_samsungDE[ inTrain,]
testing_samsungDE  <- df_samsungDE[-inTrain,]

inTrain <- createDataPartition(df_samsungCOR$galaxysentiment, p=.70, list = FALSE)
training_samsungCOR <- df_samsungCOR[ inTrain,]
testing_samsungCOR  <- df_samsungCOR[-inTrain,]

inTrain <- createDataPartition(df_samsungNZV$galaxysentiment, p=.70, list = FALSE)
training_samsungNZV <- df_samsungNZV[ inTrain,]
testing_samsungNZV  <- df_samsungNZV[-inTrain,]

inTrain <- createDataPartition(df_samsungRFE$galaxysentiment, p=.70, list = FALSE)
training_samsungRFE <- df_samsungRFE[ inTrain,]
testing_samsungRFE  <- df_samsungRFE[-inTrain,]

####Original Data Models

cl <- makeCluster(7)
registerDoParallel(cl)

ctrl <- trainControl(method = "repeatedcv", number = 5, repeats = 3)


RF_iphone_Original <- train(iphonesentiment~., data = training_iphone, method = "rf",trControl=ctrl, tuneLength = 1)
RF_samsung_Original <- train(galaxysentiment~., data = training_samsung, method = "rf",trControl=ctrl, tuneLength = 1)

SVM_iphone_Original <- train(iphonesentiment~., data = training_iphone, method = "svmLinear",trControl=ctrl, tuneLength = 3)
SVM_samsung_Original <- train(galaxysentiment~., data = training_samsung, method = "svmLinear",trControl=ctrl, tuneLength = 3)

C50_iphone_Original <- train(iphonesentiment~., data = training_iphone,method="C5.0",trControl=ctrl, tuneLength = 3)
C50_samsung_Original <- train(galaxysentiment~., data = training_samsung,method="C5.0",trControl=ctrl, tuneLength = 3)

kknn_iphone_Original<- train(iphonesentiment~., data = training_iphone, method = "kknn", trControl = ctrl, tuneLength = 3)
kknn_samsung_Original <- train(galaxysentiment~., data = training_samsung, method = "kknn", trControl = ctrl, tuneLength = 3)

###Predictions

RF_pred_iphone <- predict(RF_iphone_Original, newdata = testing_iphone)
C50_pred_iphone <- predict(C50_iphone_Original, newdata = testing_iphone)
SVM_pred_iphone <- predict(SVM_iphone_Original, newdata = testing_iphone)
KKNN_pred_iphone <- predict(kknn_iphone_Original, newdata = testing_iphone)

RF_pred_samsung <- predict(RF_samsung_Original, newdata = testing_samsung)
C50_pred_samsung <- predict(C50_samsung_Original, newdata = testing_samsung)
SVM_pred_samsung <- predict(SVM_samsung_Original, newdata = testing_samsung)
KKNN_pred_samsung <- predict(kknn_samsung_Original, newdata = testing_samsung)

cmRF_iphone <- confusionMatrix(RF_pred_iphone, testing_iphone$iphonesentiment)
cmRF_samsung <- confusionMatrix(RF_pred_samsung, testing_samsung$galaxysentiment)

cmRF_iphone

Confusion Matrix and Statistics

          Reference
Prediction    0    1    2    3    4    5
         0  374    0    1    0    5    7
         1    0    0    0    0    0    0
         2    0    0   17    0    0    0
         3    2    0    0  233    3    2
         4    2    0    1    1  128    2
         5  210  117  117  122  295 2251

Overall Statistics
                                          
               Accuracy : 0.772           
                 95% CI : (0.7585, 0.7851)
    No Information Rate : 0.5815          
    P-Value [Acc > NIR] : < 2.2e-16       
                                          
                  Kappa : 0.553           
                                          
 Mcnemar's Test P-Value : NA              

Statistics by Class:

                     Class: 0 Class: 1 Class: 2 Class: 3 Class: 4 Class: 5
Sensitivity           0.63605  0.00000  0.12500  0.65449  0.29698   0.9951
Specificity           0.99606  1.00000  1.00000  0.99802  0.99827   0.4711
Pos Pred Value        0.96641      NaN  1.00000  0.97083  0.95522   0.7233
Neg Pred Value        0.93891  0.96992  0.96927  0.96630  0.91933   0.9859
Prevalence            0.15116  0.03008  0.03496  0.09152  0.11080   0.5815
Detection Rate        0.09614  0.00000  0.00437  0.05990  0.03290   0.5787
Detection Prevalence  0.09949  0.00000  0.00437  0.06170  0.03445   0.8000
Balanced Accuracy     0.81606  0.50000  0.56250  0.82626  0.64762   0.7331

cmRF_samsung

Confusion Matrix and Statistics

          Reference
Prediction    0    1    2    3    4    5
         0  349    2    1    3    5   30
         1    0    0    1    0    1    0
         2    0    0   21    1    1    2
         3    3    2    1  152    1    9
         4    5    1    0    3  117    9
         5  151  109  111  193  300 2287

Overall Statistics
                                         
               Accuracy : 0.7559         
                 95% CI : (0.742, 0.7693)
    No Information Rate : 0.6037         
    P-Value [Acc > NIR] : < 2.2e-16      
                                         
                  Kappa : 0.4991         
                                         
 Mcnemar's Test P-Value : < 2.2e-16      

Statistics by Class:

                     Class: 0  Class: 1 Class: 2 Class: 3 Class: 4 Class: 5
Sensitivity           0.68701 0.0000000 0.155556  0.43182  0.27529   0.9786
Specificity           0.98781 0.9994677 0.998929  0.99545  0.99478   0.4368
Pos Pred Value        0.89487 0.0000000 0.840000  0.90476  0.86667   0.7258
Neg Pred Value        0.95432 0.9705350 0.970359  0.94599  0.91756   0.9306
Prevalence            0.13123 0.0294498 0.034875  0.09093  0.10979   0.6037
Detection Rate        0.09016 0.0000000 0.005425  0.03927  0.03022   0.5908
Detection Prevalence  0.10075 0.0005167 0.006458  0.04340  0.03487   0.8140
Balanced Accuracy     0.83741 0.4997338 0.577242  0.71364  0.63504   0.7077

Original Data Results

ModelData_samsung <- resamples(list(RF_iphone = RF_iphone_Original, KKNN_iphone = kknn_iphone_Original, C50_iphone = C50_iphone_Original, SVM_iphone = SVM_iphone_Original, RF_Samsung = RF_samsung_Original, KKNN_Samsung = kknn_samsung_Original, C50_Samsung = C50_samsung_Original, SVM_Samsung = SVM_samsung_Original))

summary(ModelData_samsung)

Call:
summary.resamples(object = ModelData_samsung)

Models: RF_iphone, KKNN_iphone, C50_iphone, SVM_iphone, RF_Samsung, KKNN_Samsung, C50_Samsung, SVM_Samsung 
Number of resamples: 15 

Accuracy 
                  Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
RF_iphone    0.7527533 0.7606602 0.7654185 0.7660104 0.7712639 0.7787562    0
KKNN_iphone  0.3113311 0.3242592 0.3335168 0.3299952 0.3366368 0.3432343    0
C50_iphone   0.7652893 0.7684471 0.7709251 0.7722489 0.7743530 0.7863436    0
SVM_iphone   0.7024202 0.7050400 0.7070485 0.7097144 0.7140111 0.7198679    0
RF_Samsung   0.7448810 0.7473711 0.7534549 0.7528009 0.7576009 0.7634052    0
KKNN_Samsung 0.7210847 0.7289081 0.7354732 0.7369065 0.7423279 0.7584301    0
C50_Samsung  0.7546961 0.7608516 0.7654867 0.7658571 0.7681676 0.7814056    0
SVM_Samsung  0.6810392 0.6950747 0.6981758 0.6984165 0.7019628 0.7127836    0

Kappa 
                  Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
RF_iphone    0.5099650 0.5294884 0.5381855 0.5402964 0.5513654 0.5701253    0
KKNN_iphone  0.1423081 0.1553953 0.1658034 0.1625916 0.1710681 0.1776423    0
C50_iphone   0.5433409 0.5486972 0.5545884 0.5573681 0.5614709 0.5893433    0
SVM_iphone   0.3948751 0.4006885 0.4095749 0.4151116 0.4254707 0.4402169    0
RF_Samsung   0.4717044 0.4778292 0.4932631 0.4914112 0.5003910 0.5170210    0
KKNN_Samsung 0.4653630 0.4835829 0.4903545 0.4915303 0.4968022 0.5196451    0
C50_Samsung  0.5050557 0.5204220 0.5258856 0.5307879 0.5377643 0.5712356    0
SVM_Samsung  0.3290404 0.3534472 0.3652867 0.3662064 0.3767817 0.3988142    0

###Feture Selected Data Set

#RFE Feature Selection

RF_iphone_RFE <- train(iphonesentiment~., data = training_iphoneRFE, method = "rf",trControl=ctrl, tuneLength = 1)
RF_samsung_RFE <- train(galaxysentiment~., data = training_samsungRFE, method = "rf",trControl=ctrl, tuneLength = 1)

SVM_iphone_RFE <- train(iphonesentiment~., data = training_iphoneRFE, method = "svmLinear",trControl=ctrl, tuneLength = 3)
SVM_samsung_RFE <- train(galaxysentiment~., data = training_samsungRFE, method = "svmLinear",trControl=ctrl, tuneLength = 3)

C50_iphone_RFE <- train(iphonesentiment~., data = training_iphoneRFE,method="C5.0",trControl=ctrl, tuneLength = 3)
C50_samsung_RFE <- train(galaxysentiment~., data = training_samsungRFE,method="C5.0",trControl=ctrl, tuneLength = 3)

kknn_iphone_RFE<- train(iphonesentiment~., data = training_iphoneRFE, method = "kknn", trControl = ctrl, tuneLength = 3)
kknn_samsung_RFE <- train(galaxysentiment~., data = training_samsungRFE, method = "kknn", trControl = ctrl, tuneLength = 3)

#NZV Feature Selection

RF_iphone_NZV <- train(iphonesentiment~., data = training_iphoneNZV, method = "rf",trControl=ctrl, tuneLength = 1)
RF_samsung_NZV <- train(galaxysentiment~., data = training_samsungNZV, method = "rf",trControl=ctrl, tuneLength = 1)

SVM_iphone_NZV <- train(iphonesentiment~., data = training_iphoneNZV, method = "svmLinear",trControl=ctrl, tuneLength = 3)
SVM_samsung_NZV <- train(galaxysentiment~., data = training_samsungNZV, method = "svmLinear",trControl=ctrl, tuneLength = 3)

C50_iphone_NZV <- train(iphonesentiment~., data = training_iphoneNZV,method="C5.0",trControl=ctrl, tuneLength = 3)
C50_samsung_NZV <- train(galaxysentiment~., data = training_samsungNZV,method="C5.0",trControl=ctrl, tuneLength = 3)

kknn_iphone_NZV<- train(iphonesentiment~., data = training_iphoneNZV, method = "kknn", trControl = ctrl, tuneLength = 3)
kknn_samsung_NZV <- train(galaxysentiment~., data = training_samsungNZV, method = "kknn", trControl = ctrl, tuneLength = 3)

#COR Feature Selection

RF_iphone_COR <- train(iphonesentiment~., data = training_iphoneCOR, method = "rf",trControl=ctrl, tuneLength = 1)
RF_samsung_COR <- train(galaxysentiment~., data = training_samsungCOR, method = "rf",trControl=ctrl, tuneLength = 1)

SVM_iphone_COR <- train(iphonesentiment~., data = training_iphoneCOR, method = "svmLinear",trControl=ctrl, tuneLength = 3)
SVM_samsung_COR <- train(galaxysentiment~., data = training_samsungCOR, method = "svmLinear",trControl=ctrl, tuneLength = 3)

C50_iphone_COR <- train(iphonesentiment~., data = training_iphoneCOR,method="C5.0",trControl=ctrl, tuneLength = 3)
C50_samsung_COR <- train(galaxysentiment~., data = training_samsungCOR,method="C5.0",trControl=ctrl, tuneLength = 3)

kknn_iphone_COR<- train(iphonesentiment~., data = training_iphoneCOR, method = "kknn", trControl = ctrl, tuneLength = 3)
kknn_samsung_COR <- train(galaxysentiment~., data = training_samsungCOR, method = "kknn", trControl = ctrl, tuneLength = 3)

#DE Feature Selection

RF_iphone_DE <- train(iphonesentiment~., data = training_iphoneDE, method = "rf",trControl=ctrl, tuneLength = 1)
RF_samsung_DE <- train(galaxysentiment~., data = training_samsungDE, method = "rf",trControl=ctrl, tuneLength = 1)

SVM_iphone_DE <- train(iphonesentiment~., data = training_iphoneDE, method = "svmLinear",trControl=ctrl, tuneLength = 3)
SVM_samsung_DE <- train(galaxysentiment~., data = training_samsungDE, method = "svmLinear",trControl=ctrl, tuneLength = 3)

C50_iphone_DE <- train(iphonesentiment~., data = training_iphoneDE,method="C5.0",trControl=ctrl, tuneLength = 3)
C50_samsung_DE <- train(galaxysentiment~., data = training_samsungDE,method="C5.0",trControl=ctrl, tuneLength = 3)

kknn_iphone_DE<- train(iphonesentiment~., data = training_iphoneDE, method = "kknn", trControl = ctrl, tuneLength = 3)
kknn_samsung_DE <- train(galaxysentiment~., data = training_samsungDE, method = "kknn", trControl = ctrl, tuneLength = 3)

###All Results

ModelData_All_iPhone <- resamples(list(RF_iphone=RF_iphone_Original, 
                                    RF_iphone_DE=RF_iphone_DE, 
                                    RF_iphone_COR=RF_iphone_COR, 
                                    RF_iphone_NZV=RF_iphone_NZV, 
                                    RF_iphone_RFE=RF_iphone_RFE,
                                    
                                    C50_iphone=C50_iphone_Original, 
                                    C50_iphone_DE=C50_iphone_DE, 
                                    C50_iphone_COR=C50_iphone_COR, 
                                    C50_iphone_NZV=C50_iphone_NZV, 
                                    C50_iphone_RFE=C50_iphone_RFE,
                                    
                                    SVM_iphone=SVM_iphone_Original, 
                                    SVM_iphone_DE=SVM_iphone_DE, 
                                    SVM_iphone_COR=SVM_iphone_COR, 
                                    SVM_iphone_NZV=SVM_iphone_NZV, 
                                    SVM_iphone_RFE=SVM_iphone_RFE,
                                    
                                    kknn_iphone=kknn_iphone_Original, 
                                    kknn_iphone_DE=kknn_iphone_DE, 
                                    kknn_iphone_COR=kknn_iphone_COR, 
                                    kknn_iphone_NZV=kknn_iphone_NZV, 
                                    kknn_iphone_RFE=kknn_iphone_RFE
                                    ))

ModelData_All_Samsung <- resamples(list(RF_samsung=RF_samsung_Original, 
                                    RF_samsung_DE=RF_samsung_DE, 
                                    RF_samsung_COR=RF_samsung_COR, 
                                    RF_samsung_NZV=RF_samsung_NZV, 
                                    RF_samsung_RFE=RF_samsung_RFE,
                                    
                                    C50_samsung=C50_samsung_Original, 
                                    C50_samsung_DE=C50_samsung_DE, 
                                    C50_samsung_COR=C50_samsung_COR, 
                                    C50_samsung_NZV=C50_samsung_NZV, 
                                    C50_samsung_RFE=C50_samsung_RFE,
                                    
                                    SVM_samsung=SVM_samsung_Original, 
                                    SVM_samsung_DE=SVM_samsung_DE, 
                                    SVM_samsung_COR=SVM_samsung_COR, 
                                    SVM_samsung_NZV=SVM_samsung_NZV, 
                                    SVM_samsung_RFE=SVM_samsung_RFE,
                                    
                                    kknn_samsung=kknn_samsung_Original, 
                                    kknn_samsung_DE=kknn_samsung_DE, 
                                    kknn_samsung_COR=kknn_samsung_COR, 
                                    kknn_samsung_NZV=kknn_samsung_NZV, 
                                    kknn_samsung_RFE=kknn_samsung_RFE
                                    ))

summary(ModelData_All_iPhone)

Call:
summary.resamples(object = ModelData_All_iPhone)

Models: RF_iphone, RF_iphone_DE, RF_iphone_COR, RF_iphone_NZV, RF_iphone_RFE, C50_iphone, C50_iphone_DE, C50_iphone_COR, C50_iphone_NZV, C50_iphone_RFE, SVM_iphone, SVM_iphone_DE, SVM_iphone_COR, SVM_iphone_NZV, SVM_iphone_RFE, kknn_iphone, kknn_iphone_DE, kknn_iphone_COR, kknn_iphone_NZV, kknn_iphone_RFE 
Number of resamples: 15 

Accuracy 
                     Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
RF_iphone       0.7527533 0.7606602 0.7654185 0.7660104 0.7712639 0.7787562    0
RF_iphone_DE    0.6486784 0.6507981 0.6541850 0.6541534 0.6555614 0.6615215    0
RF_iphone_COR   0.6626307 0.6708869 0.6740088 0.6738604 0.6780407 0.6813671    0
RF_iphone_NZV   0.7443526 0.7539901 0.7577093 0.7583383 0.7643828 0.7688498    0
RF_iphone_RFE   0.7619571 0.7702883 0.7757576 0.7747099 0.7799500 0.7830396    0
C50_iphone      0.7652893 0.7684471 0.7709251 0.7722489 0.7743530 0.7863436    0
C50_iphone_DE   0.6439185 0.6465731 0.6507151 0.6512535 0.6540052 0.6674009    0
C50_iphone_COR  0.6567493 0.6688687 0.6721672 0.6707760 0.6749244 0.6784141    0
C50_iphone_NZV  0.7479362 0.7497247 0.7544053 0.7549275 0.7592292 0.7654185    0
C50_iphone_RFE  0.7538546 0.7693369 0.7721519 0.7722850 0.7783590 0.7830396    0
SVM_iphone      0.7024202 0.7050400 0.7070485 0.7097144 0.7140111 0.7198679    0
SVM_iphone_DE   0.5990099 0.6031353 0.6081453 0.6082783 0.6121045 0.6193619    0
SVM_iphone_COR  0.6505228 0.6549162 0.6565768 0.6570518 0.6584099 0.6659329    0
SVM_iphone_NZV  0.6688705 0.6799670 0.6831683 0.6837318 0.6875688 0.6953168    0
SVM_iphone_RFE  0.6875688 0.6958426 0.7046832 0.7018633 0.7070150 0.7140496    0
kknn_iphone     0.3113311 0.3242592 0.3335168 0.3299952 0.3366368 0.3432343    0
kknn_iphone_DE  0.2753304 0.2854394 0.2944414 0.2931132 0.2993385 0.3074807    0
kknn_iphone_COR 0.1922865 0.2007701 0.2031938 0.2038241 0.2069913 0.2124381    0
kknn_iphone_NZV 0.3036304 0.3117773 0.3193833 0.3203113 0.3297550 0.3357222    0
kknn_iphone_RFE 0.3238043 0.3314067 0.3346175 0.3387686 0.3461745 0.3595815    0

Kappa 
                      Min.    1st Qu.    Median       Mean   3rd Qu.       Max. NA's
RF_iphone       0.50996496 0.52948841 0.5381855 0.54029638 0.5513654 0.57012534    0
RF_iphone_DE    0.24203267 0.24881475 0.2536719 0.25685508 0.2598509 0.27716271    0
RF_iphone_COR   0.28609913 0.30843701 0.3159714 0.31690543 0.3287299 0.33501884    0
RF_iphone_NZV   0.49811202 0.51647615 0.5253460 0.52682907 0.5408159 0.54954349    0
RF_iphone_RFE   0.53493534 0.55188763 0.5617076 0.56200788 0.5737136 0.58070746    0
C50_iphone      0.54334094 0.54869724 0.5545884 0.55736812 0.5614709 0.58934333    0
C50_iphone_DE   0.23054282 0.23726041 0.2522310 0.25093415 0.2592462 0.29256443    0
C50_iphone_COR  0.28359364 0.30768331 0.3139249 0.31470938 0.3271151 0.33293018    0
C50_iphone_NZV  0.50231444 0.50868731 0.5170771 0.51931132 0.5270671 0.54365480    0
C50_iphone_RFE  0.51621618 0.54972052 0.5599136 0.55803825 0.5721061 0.58157193    0
SVM_iphone      0.39487506 0.40068848 0.4095749 0.41511164 0.4254707 0.44021686    0
SVM_iphone_DE   0.07506227 0.08931142 0.1039479 0.10263402 0.1139134 0.14361741    0
SVM_iphone_COR  0.25041839 0.26252328 0.2673713 0.26839347 0.2727810 0.28999175    0
SVM_iphone_NZV  0.31532691 0.34450251 0.3493697 0.35058385 0.3607934 0.38019645    0
SVM_iphone_RFE  0.36422870 0.39101839 0.4074289 0.40244334 0.4143686 0.42962060    0
kknn_iphone     0.14230806 0.15539530 0.1658034 0.16259161 0.1710681 0.17764234    0
kknn_iphone_DE  0.09441844 0.10780845 0.1215946 0.11646001 0.1233551 0.13232911    0
kknn_iphone_COR 0.04231185 0.05131120 0.0533050 0.05543538 0.0597170 0.06968645    0
kknn_iphone_NZV 0.12367763 0.13809726 0.1432977 0.14455215 0.1521444 0.16060356    0
kknn_iphone_RFE 0.15560938 0.16278367 0.1686654 0.17199882 0.1806159 0.19858417    0

summary(ModelData_All_Samsung)

Call:
summary.resamples(object = ModelData_All_Samsung)

Models: RF_samsung, RF_samsung_DE, RF_samsung_COR, RF_samsung_NZV, RF_samsung_RFE, C50_samsung, C50_samsung_DE, C50_samsung_COR, C50_samsung_NZV, C50_samsung_RFE, SVM_samsung, SVM_samsung_DE, SVM_samsung_COR, SVM_samsung_NZV, SVM_samsung_RFE, kknn_samsung, kknn_samsung_DE, kknn_samsung_COR, kknn_samsung_NZV, kknn_samsung_RFE 
Number of resamples: 15 

Accuracy 
                      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
RF_samsung       0.7448810 0.7473711 0.7534549 0.7528009 0.7576009 0.7634052    0
RF_samsung_DE    0.6192584 0.6221669 0.6229961 0.6247413 0.6272125 0.6334992    0
RF_samsung_COR   0.6727474 0.6827978 0.6875000 0.6867631 0.6912861 0.6954596    0
RF_samsung_NZV   0.7466814 0.7513819 0.7570559 0.7561211 0.7590597 0.7686774    0
RF_samsung_RFE   0.7497238 0.7555309 0.7614831 0.7615425 0.7670172 0.7759956    0
C50_samsung      0.7546961 0.7608516 0.7654867 0.7658571 0.7681676 0.7814056    0
C50_samsung_DE   0.6196013 0.6205751 0.6232044 0.6233044 0.6239978 0.6325401    0
C50_samsung_COR  0.6751522 0.6813157 0.6838317 0.6836665 0.6873099 0.6913717    0
C50_samsung_NZV  0.7415606 0.7482014 0.7516593 0.7518426 0.7553889 0.7627212    0
C50_samsung_RFE  0.7504151 0.7564271 0.7606412 0.7608750 0.7629323 0.7795580    0
SVM_samsung      0.6810392 0.6950747 0.6981758 0.6984165 0.7019628 0.7127836    0
SVM_samsung_DE   0.6209945 0.6218534 0.6241017 0.6241518 0.6261062 0.6277655    0
SVM_samsung_COR  0.6624239 0.6700774 0.6709071 0.6717168 0.6737626 0.6815920    0
SVM_samsung_NZV  0.6718318 0.6759817 0.6790055 0.6794974 0.6828869 0.6882255    0
SVM_samsung_RFE  0.6742257 0.6829741 0.6858407 0.6851397 0.6874135 0.6976230    0
kknn_samsung     0.7210847 0.7289081 0.7354732 0.7369065 0.7423279 0.7584301    0
kknn_samsung_DE  0.1024363 0.1065300 0.1072416 0.1790937 0.1238697 0.6209186    0
kknn_samsung_COR 0.2472345 0.6334997 0.6426991 0.5953944 0.6586445 0.6738530    0
kknn_samsung_NZV 0.3861878 0.6816786 0.7232983 0.6628759 0.7423914 0.7508306    0
kknn_samsung_RFE 0.4327615 0.5907724 0.7302377 0.6576406 0.7366528 0.7472345    0

Kappa 
                        Min.    1st Qu.     Median       Mean    3rd Qu.       Max. NA's
RF_samsung       0.471704443 0.47782923 0.49326312 0.49141116 0.50039096 0.51702103    0
RF_samsung_DE    0.080102288 0.08973244 0.09277634 0.09933491 0.11055355 0.12675442    0
RF_samsung_COR   0.279823757 0.30589920 0.31570433 0.31410672 0.32615722 0.33523363    0
RF_samsung_NZV   0.484395520 0.49293198 0.50646251 0.50561755 0.51350313 0.53553756    0
RF_samsung_RFE   0.497402822 0.50453513 0.51863941 0.52068620 0.53366370 0.55353452    0
C50_samsung      0.505055743 0.52042198 0.52588564 0.53078789 0.53776430 0.57123557    0
C50_samsung_DE   0.074867518 0.08393829 0.08938664 0.09092923 0.09499727 0.11578560    0
C50_samsung_COR  0.273053308 0.29479059 0.30462978 0.30328561 0.31523558 0.32286941    0
C50_samsung_NZV  0.470230027 0.48540468 0.49807960 0.49684250 0.50849985 0.52419389    0
C50_samsung_RFE  0.494873470 0.51180857 0.52080839 0.52063059 0.52584749 0.56390783    0
SVM_samsung      0.329040440 0.35344724 0.36528667 0.36620641 0.37678172 0.39881421    0
SVM_samsung_DE   0.080310439 0.08509425 0.09485042 0.09388744 0.10190785 0.10888411    0
SVM_samsung_COR  0.245610109 0.26445854 0.26865324 0.27064970 0.27643416 0.30034144    0
SVM_samsung_NZV  0.294191474 0.30375774 0.31298348 0.31420041 0.32086661 0.33580192    0
SVM_samsung_RFE  0.310797394 0.33425984 0.33770745 0.33781919 0.34123333 0.37426061    0
kknn_samsung     0.465362960 0.48358292 0.49035445 0.49153031 0.49680220 0.51964512    0
kknn_samsung_DE  0.002185782 0.01117107 0.01296818 0.02125110 0.01548823 0.09799522    0
kknn_samsung_COR 0.084024358 0.23201955 0.27707846 0.25561741 0.31269379 0.32855773    0
kknn_samsung_NZV 0.195501328 0.40746971 0.44024950 0.40904987 0.48054266 0.50679814    0
kknn_samsung_RFE 0.235076982 0.35572479 0.48181726 0.42178075 0.49190294 0.50327961    0

##Large Matrices

dfLM_iphone <- import("LargeMatrix_iphone.csv")
dfLM_samsung <- import("LargeMatrix_samsung.csv")

dfLM_iphoneRFE <- dfLM_iphone[,predictors(rfeResults_iphone)]
dfLM_iphoneRFE$iphonesentiment <- dfLM_iphone$iphonesentiment

#No feature selection for Samsung

LM_Pred_iphone <- predict(RF_iphone_RFE, newdata = dfLM_iphoneRFE)
LM_Pred_Samsung <- predict(C50_samsung_Original, newdata = dfLM_samsung)

summary(LM_Pred_iphone)

    0     1     2     3     4     5 
44725     0  3029  2071     2 15021 

summary(LM_Pred_Samsung)

    0     1     2     3     4     5 
39022     0  4482  2301    84 18959 

summary(df_iphone$iphonesentiment)

   0    1    2    3    4    5 
1962  390  454 1188 1439 7540 

summary(df_samsung$galaxysentiment)

   0    1    2    3    4    5 
1696  382  450 1175 1417 7791